DE102019005431A1 - 3D model generation device - Google Patents

Abstract

A 3D model generation device generates individual models, which suggest the individual shape of at least two objects, on the basis of an integrated model which is generated based on data obtained by jointly imaging or measuring the objects. The 3D model generating device generates a plurality of partial models by dividing the integrated model with extension planes, which are obtained by expanding areas delimiting the integrated model, determined on the basis of the data obtained, two-dimensional regions in which the objects are present individually, based on the partial models Projections of the sub-models and the two-dimensional areas with tags and generates the individual models of the objects on the basis of the tagged sub-models.

Description

BACKGROUND OF THE INVENTION

Field of the Invention

The present invention relates to a 3D model generation device or device for generating a three-dimensional (3D) model, and in particular to a 3D model generation device which is set up to generate collision check data using images.

Description of the related art

Technologies exist for the detection of collisions between machine tool structures, tools and workpieces. A 3D collision checking function as a conventional collision detection technology is generally based on a method in which a three-dimensional shape of a collision checking object is represented by a combination of stereo models such as cuboids and cylinders, and a three-dimensional simulation is performed to check whether the stereo models collide with each other.

When checking the collision using the 3D collision checking function, three-dimensional models generated by CAD (computer-aided design) are required as three-dimensional simulation data. However, a workpiece to be machined and a jig used to fix the workpiece vary in each machining process performed by a machine tool, so that the three-dimensional models must be generated by an operator each time. Although the workpiece changes shape as it is machined by a tool (or in contact with the tool), the chuck generally never changes shape and is an object whose contact with the tool is a collision. The workpiece and the clamping device should therefore be created as separate three-dimensional models.

The Japanese Patent No. 4083554 teaches as a technology to support the generation of three-dimensional models a process in which image data is generated by means of individual imaging of structures forming a machine tool in the direction of the x, y and z axes using two cameras and three-dimensional shape data of the structures based on the individual image data be generated.

It also teaches Japanese Patent No. 4456455 a technology in which, based on the respective images of a chuck and a workpiece in a lathe, shapes are recognized in a fastened and a non-fastened state in order to calculate collision areas.

This also teaches Japanese Patent No. 6043234 a technology in which a single model of a clamping device is generated based on a three-dimensional model of a workpiece and data obtained by integrally measuring the shape of the workpiece and the clamping device by means of a three-dimensional measurement.

At the in the Japanese Patent No. 4083554 conventional technology, the workpiece and the clamping device are inevitably generated as an integrated three-dimensional model and cannot be differentiated from one another by this three-dimensional model. Therefore, the workpiece and the clamping device cannot be distinguished from one another in a collision check.

In addition, in the Japanese Patent No. 4456455 technology, the respective images of the workpiece and the chuck (or the clamping device) in the fastened and unsecured state are recorded separately when the three-dimensional model is generated, so that it cannot be assumed that the time and effort required to produce the three-dimensional model in full Scope is minimized.

In addition, in the Japanese Patent No. 6043234 technology, the three-dimensional model of the clamping device is cut out using the three-dimensional model of the workpiece from the integrated three-dimensional model combining the workpiece and the clamping device. However, the three-dimensional model of the workpiece must be created separately by an operator using CAD. Thus, the operator must create the three-dimensional model of the workpiece, although he / she does not have to deal with the generation of the three-dimensional model of the jig.

SUMMARY OF THE INVENTION

Accordingly, the object of the present invention is to provide a 3D model generation device which is capable of automatically generating three-dimensional models of a workpiece and a clamping device on the basis of imaging or measurement data.

A 3D model generation device of the present invention, which generates individual models, which suggest the individual shape of at least two objects, on the basis of an integrated model which is generated on the basis of data obtained by jointly imaging or measuring the objects, comprises a 3D model division processing unit, which is configured to generate a plurality of partial models by dividing the integrated model with expansion planes which are obtained by expanding surfaces delimiting the integrated model, an area determination unit which is configured to determine two-dimensional areas based on the data obtained to which the objects are present individually, and a single model generation unit which is set up to tag the partial models based on projections of the partial models and the two-dimensional regions and to provide the individual models of the objects with tags to produce partial models.

In one embodiment of the 3D model generation device of the present invention, the objects include a workpiece and a chuck.

In one embodiment of the 3D model generating device of the present invention, the area determining unit determines the two-dimensional areas based on luminance information or color information of recorded images of the objects.

In one embodiment of the 3D model generation device of the present invention, depending on the degree of overlap between the projections of the partial models and the two-dimensional regions of the determined objects, the single model generation unit attaches tags to the partial models that indicate the determined objects.

According to the present invention, a 3D model generation device can be provided which is capable of automatically generating three-dimensional models of a workpiece and a clamping device based on imaging or measurement data.

list of figures

• 1 eine schematische Hardwarekonfigurationsdarstellung, die wesentliche Teile einer 3D-Modellerzeugungsvorrichtung gemäß einer Ausführungsform der vorliegenden Erfindung zeigt;
• 2 ein schematisches Funktionsblockdiagramm der 3D-Modellerzeugungsvorrichtung gemäß einer Ausführungsform der vorliegenden Erfindung;
• 3 eine Darstellung, die ein Verfahren zur Erzeugung eines dreidimensionalen Modells durch Stereo-Vision zeigt;
• 4 eine Ansicht, die ein Beispiel für ein Verfahren zum Aufteilen eines integrierten Modells zeigt;
• 5 eine Ansicht, die ein Beispiel für ein Verfahren zum Unterscheiden von konkaven und konvexen Kanten zeigt;
• 6 eine Ansicht, die eine durch eine 3D-Modellerzeugungsdatenerfassungseinheit und eine Bereichsbestimmungsdatenerfassungseinheit durchgeführte Verarbeitung zeigt;
• 7 eine Ansicht, die durch eine 3D-Modellerzeugungseinheit und einen 3D-Modellteilungsprozessor durchgeführte Verarbeitungen zeigt;
• 8 eine Ansicht, die eine durch eine Bereichsbestimmungseinheit durchgeführte Verarbeitung zeigt;
• 9 eine Ansicht, die eine durch eine Einzelmodellerzeugungseinheit durchgeführte Verarbeitung zeigt;
• 10 eine Ansicht, die eine durch die Einzelmodellerzeugungseinheit durchgeführte Verarbeitung zeigt; und
• 11 eine Ansicht, die eine durch die Einzelmodellerzeugungseinheit durchgeführte Verarbeitung zeigt.

The above and other objects and features of the present invention will become apparent from the following description of the embodiments with reference to the accompanying drawings. It shows:

• 1 is a schematic hardware configuration diagram showing essential parts of a 3D model generation device according to an embodiment of the present invention;
• 2 a schematic functional block diagram of the 3D model generating device according to an embodiment of the present invention;
• 3 a diagram showing a method for generating a three-dimensional model by stereo vision;
• 4 11 is a view showing an example of a method for dividing an integrated model;
• 5 11 is a view showing an example of a method for distinguishing concave and convex edges;
• 6 12 is a view showing processing performed by a 3D model generation data acquisition unit and an area determination data acquisition unit;
• 7 11 is a view showing processing performed by a 3D model generation unit and a 3D model sharing processor;
• 8th 11 is a view showing processing performed by an area determination unit;
• 9 11 is a view showing processing performed by a single model generation unit;
• 10 Fig. 14 is a view showing processing performed by the single model generation unit; and
• 11 14 is a view showing processing performed by the single model generation unit.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

A configuration example of a 3D model generation device embodying the present invention is described below.

1 FIG. 12 is a schematic hardware configuration diagram showing essential parts of a 3D model generation device 1 according to an embodiment of the present invention. The 3D model generating device 1 according to the present embodiment can be implemented, for example, as a numerical control device. In addition, the 3D model generation device 1 according to the present embodiment can be implemented as a workstation or the like, which, for example, together with a Machine tool is installed. Furthermore, the 3D model generating device 1 according to the present embodiment can also be designed as a collision checking device or the like, which is installed, for example, together with a machine tool. 1 shows an example of the hardware configuration of the 3D model generating device 1 designed as a workstation.

The 3D model generation device 1 comprises a processor 10 as a central component. Individual components of the 3D model generation device 1 are by a bus 17 interconnected and swap over the bus 17 data from one another. The processor 10 controls the entire 3D model generating device 1 according to one in ROM (read-only memory) 11 stored system program. As a ROM 11 For example, an EPROM (erasable programmable read only memory), an EEPROM (electrically erasable programmable read only memory) or the like can be used.

A DRAM (dynamic RAM) or the like can be used as RAM (random access memory) 12 are used in which temporary calculation data, display data, input and output signals, etc. are loaded. As a non-volatile memory 13 For example, CMOS (Complementary Metal Oxide Semiconductor), SRAM (Static RAM), or the like can be used, which are supported by a battery (not shown). The non-volatile memory 13 stores parameters and the like that can be obtained even after a power cut.

A machine control panel 18 , which is located, for example, on the front side of the 3D model generating device 1, receives a display of data and graphics required for operating the 3D model generating device 1, manual operator input by an operator, data input and the like and becomes used to operate the 3D model generating device 1 used. A graphics control circuit 19 converts digital signals, such as numerical data and graphic data, into raster signals for display and forwards them to a display device 20 further. The display device 20 then displays these numerical values and graphs. As a display device 20 a liquid crystal display device is mainly used.

An input device 21 includes a keyboard equipped with key switches, rotary switches, number keys, symbol keys, letter keys and function keys, and a pointing device such as a mouse.

A touch panel 22 has a function for recognizing an operation performed by the operator, such as touching or pulling. The touch panel 22 overlays the screen of the display device 20 so that it is his / her operation of a software button, a software button and a software switch that are on the screen of the display device 20 can be displayed. Alternatively, you can use the touch panel 22 and the display device 20 run together as a single unit.

A communication facility 23 performs data communication between a numerical control device, a collision checking device, a cell computer, a host computer and the like via a wired / wireless network. 3D model data generated in the 3D model generating device 1 are transmitted via the communication device 23 or the like is transmitted to the numerical control device.

An interface 14 is an interface through which an image or measurement using a sensor 100 obtained data of the 3D model generating device 1 are supplied. The sensor 100 can be any sensor that can acquire data to generate a three-dimensional model. A camera or a distance sensor can be used, for example, as a sensor 100 be used. The sensor used can be more preferred 100 a 3D distance image camera, a stereo vision camera or the like, which can capture an image of an object to be imaged and the distance of each pixel of the image to its imaging position.

An interface 15 is an interface through which an image is mapped using a sensor 102 obtained data of the 3D model generating device 1 are supplied. The sensor 102 can be any sensor that can detect information that can be used to differentiate between a workpiece and a clamping device. In some cases, the luminance and color (optical wavelength) of the surface can vary depending on, for example, the material difference between the workpiece and the clamping device. Therefore, a camera can typically be used as a sensor 102 be used. Information about the luminance, color (optical wavelength) and the like are obtained on the basis of image data captured by the camera. In addition, the deviation of the optical wavelength due to the material difference can be more accurately distinguished by using a high performance camera such as a hyperspectral camera. The sensor 102 is preferably set up to output parameters such as the viewing angle, the camera orientation and the distance to the object in the image to the outside. Alternatively, the sensor 102 preferably used in a previously calibrated state so that the parameters are determined.

The sensors 100 and 102 can be independent institutions. Alternatively, a single device can be used as the two sensors 100 and 102 acts.

2 FIG. 10 is a schematic functional block diagram showing essential parts of the 3D model generation device according to an embodiment of the present invention in the case where the system program for implementing a 3D model generation function of the present invention is shown in FIG 1 3D model generating device 1 shown is executed. In the 2 Function blocks shown are implemented when the processor 10 in the in 1 3D model generation device 1 shown executes the system program for the 3D model generation function and controls the operation of the individual parts of the 3D model generation device 1. The 3D model generation device 1 of the present embodiment includes a 3D model generation data acquisition unit 110 , a 3D model generation unit 120 , a 3D model sharing processor 130 , a single model generation unit 150 , an area determination data acquisition unit 160 and an area determining unit 170 , There is also a 3D model generation data storage 200 and a 3D model memory 210 in the non-volatile memory 13 of the 3D model generating device 1 inserted. The 3D model generation data storage 200 is used to store images obtained by imaging or measuring the workpiece and the jig to which the workpiece is attached. The 3D model memory 210 is used to save the three-dimensional model.

The 3D model generation data acquisition unit 110 is a functional unit that is set up by imaging or measuring by means of the sensor 100 to acquire the data obtained and the data in the 3D model generation data memory 200 to load (see 6 ). The 3D -Modellerzeugungsdatenerfassungseinheit 110 can be set up to contain a plurality of data records which, as in 6 shown, for example by imaging or measuring a workpiece 320 and a jig 322 on which the workpiece 320 is attached in a plurality of directions by the sensor 100 are captured in the 3D model generation data memory 200 to load.

The 3D model generation unit 120 is a functional unit that is set up to generate the three-dimensional model on the basis of data generated by jointly imaging or measuring the workpiece 320 and the clamping device 322 on which the workpiece 320 attached, preserved and in the 3D model generation data storage 200 are saved (see 7 ). The 3D -Modellerzeugungseinheit 120 loads this based on the data in the 3D model generation data storage 200 stored data generated three-dimensional model as the workpiece 320 and the jig 322 Combining integrated model in the 3D model memory 210 ,

Various methods, such as the volume intersection method and stereo matching method, are generally known as methods for generating a three-dimensional model from images as data. The method for generating the three-dimensional model by the 3D model generation unit 120 however, can be any method based on the result of imaging or measuring the workpiece, acquired in any way 320 and the clamping device 322 on which the workpiece 320 is attached, which can generate three-dimensional model.

The following is a brief description of a method using three-dimensional distance images as an example of the 3D model generation by the 3D model generation unit 120 , In this method, the 3D model generation data acquisition unit 110 initially used to create a plurality of distance images by imaging the workpiece together 320 and the clamping device 322 on which the workpiece 320 is attached in a plurality of directions by the 3D distance image camera, stereo vision camera or the like as a sensor 100 be loaded into the 3D model generation data memory 200. If the 3D distance image camera is used to take distance images, it can be installed in a predetermined position beforehand or, for example, attached to the spindle of a machine tool or a robot that is installed together with the machine tool, so that the 3D distance image camera is axially to the position for the illustration can be moved. In addition, as in 3 shown, the stereo vision camera used to capture the images of the object, wherein the distance images are obtained according to the following steps.

Step a1: Feature points are recorded in images.

Step a2: The feature points between the images (an image of the right eye (X _R , Y _R ) and an image of the left eye (X _L , Y _L ) in 3 ) are assigned to each other.

$$\text{Y}=\left\{\text{B/}\left({\text{X}}_{\text{L}}-{\text{X}}_{\text{R}}\right)\right\}*{\text{Y}}_{\text{L}}$$

$$\text{Z}=\left\{\text{B/}\left({\text{X}}_{\text{L}}-{\text{X}}_{\text{R}}\right)\right\}*\text{f}$$

wobei die Glieder f und B eine Brennweite bzw. eine Basislinienlänge sind.Step a3: Based on the recognized feature points, a three-dimensional position is calculated according to the following formulas: $$\text{X}=\left\{\text{B /}\left({\text{X}}_{\text{L}}-{\text{X}}_{\text{R}}\right)\right\}*{\text{X}}_{\text{L}}$$

$$\text{Y}=\left\{\text{B /}\left({\text{X}}_{\text{L}}-{\text{X}}_{\text{R}}\right)\right\}*{\text{Y}}_{\text{L}}$$

$$\text{Z}=\left\{\text{B /}\left({\text{X}}_{\text{L}}-{\text{X}}_{\text{R}}\right)\right\}*\text{f}$$

the terms f and B being a focal length and a baseline length, respectively.

The 3D model generation unit 120 aligns the recorded images for a plurality of distance images obtained in this way by parallel translation and rotation with the same coordinate system. The 3D model generation unit receives using the plurality of distance images aligned with the same coordinate system 120 a signed distance to a voxel (grid point) to create a grid using the Marching Cubes method.

The 3D model generation unit also generates 120 a simplified three-dimensional model for the grid generated in the above manner according to the following steps.

Step b1: The normal to each grid area of the three-dimensional model is calculated.

Step b2: An external product is calculated for normal to neighboring surfaces.

Step b3: If the calculated outer product is not higher than a predetermined threshold value, the adjacent areas are considered identical and synthesized.

The 3D model sharing processor 130 is a functional unit that is set up based on the workpiece 320 and the jig 322 combining integrated model that in the 3D model memory 210 is saved to create sub-models by dividing each part of the integrated model (see 7 ). The 3D model sharing processor 130 shares the integrated model as in 4 shown along the expansion levels 304a and 304b by expanding the areas delimiting the integrated model 302a and 302b be obtained in the direction of the respective arrows E1 and E2 on. The 3D model sharing processor 130 loads the partial models into the 3D model memory 210 , the sub-models by dividing the in the 3D model memory 210 stored integrated model can be obtained.

There are various algorithms for an algorithm for the division of the integrated model by the 3D model division processor 130 to disposal. As an example of the division algorithm, it can be determined whether an edge (boundary line at which surfaces touch each other) is concave or convex on each part of the integrated model, so that the surfaces can be expanded to a position in the binary direction (positive or negative direction of a binormal vector) of the surface that is in contact with the concave edge, another edge is crossed to divide the model at the crossing point. If this procedure is used, the 3D model sharing processor determines 130 for example, according to the following steps, whether the edge (boundary line at which the surfaces touch each other) is concave or convex on each part of the integrated model (see 6 ).

Step c1: respective normal vectors 310a and 310b (to the front of an object) first and second surfaces 308a and 308b (of which the second area 308b (viewed from the front of the object, is an area to the right of the edge vector) that are in contact with the edge to be distinguished are obtained.

Step c2: A binomial vector 314 becomes for the normal vector 310b the second surface 308b and an edge vector 312 receive.

Step c3: The inner product of the normal vector 310a the first area 308a and the obtained binormal vector 314 will get. If the inner product is negative, it is determined that the edge is convex. If the inner product is positive, it is determined that the edge is concave.

Since the above 3D model division algorithm is already from “Decomposition of a Welded Part by Interactive Loop Generation Based on Multiple Feature Recognition” (Journal of the Japan Society for Precision Engineering, Volume 62 , No. 12, pages 1707 - 1711 , well known from TaeSung Yoon et al., The Japan Society for Precision Engineering) or the like, further detailed description thereof is omitted herein.

The area determination data acquisition unit 160 is a functional unit that is set up to collect data by imaging or measuring the workpiece 320 and the clamping device 322 by means of the sensor 102 be obtained (see 7 ). The area determination data acquisition unit 160 can acquire image data including, for example, luminance information, color information, depth information or X-ray transmission information.

The area determination unit 170 is a functional unit that is set up in the by the Area determination data acquisition unit 160 captured image data on the workpiece 320 located area 330 and one on the jig 322 located area 332 to be distinguished from each other (see 8th ). The area determination unit 170 can be set up on the workpiece 320 located area 330 and the one on the clamping device 322 located area 332 distinguish from each other by any method based on various information in the area determination data acquisition unit 160 captured image data such as luminance information, color information and the like are included.

The following is a description of an exemplary method in which the area determining unit 170 on the workpiece 320 located area 330 and the one on the clamping device 322 located area 332 using the luminance or color information. If for the workpiece 320 and the jig 322 If different material qualities (including different materials and surface treatment types) are used, the luminance or color (optical wavelength) in the image data can sometimes vary between the two elements. In this case, the area determination unit determines 170 in the area determination data acquisition unit 160 captured image data an area in which a pixel with a luminance or color (optical wavelength) typical of the workpiece is present, and an area in which a pixel with a luminance or color typical for the clamping device (optical wavelength) is present. It is assumed that the reference values of the luminance or color typical of the workpiece and of the luminance or color (optical wavelength) typical of the clamping device in advance by the range determination unit 170 get saved. The area determination unit 170 can use the defined reference values to determine a pixel with a luminance or color (optical wavelength) within a defined range than that on the workpiece 320 located area 330 or on the clamping device 322 determine the area.

There follows a description of another exemplary method in which the area determining unit 170 on the workpiece 320 located area 330 and the one on the clamping device 322 located area 332 distinguished from one another by shape determination. This procedure is effective when the workpiece 320 and the jig 322 have a certain characteristic shape. In this case, the area determination unit stores 170 a learning model that features a shape of the workpiece by a known machine learning method 320 and the clamping device 322 has learned so that she can use this learning model to determine whether the generated sub-model is the workpiece 320 or the clamping device 322 is.

The single model generation unit 150 is a functional unit that is set up to be that of the 3D model sharing processor 130 generated sub-models that the workpiece 320 or the clamping device 322 corresponds, based on that by the area determination unit 170 obtained results of the differentiation of the areas located on the workpiece and the clamping device 330 and 332 to be individually tagged and to create a single model which is an individual model based on submodels provided with the same tag.

wobei das klein geschriebene x eine Koordinate in den durch die Bereichsbestimmungsdatenerfassungseinheit 160 erfassten Bilddaten, das groß geschriebene X eine Koordinate im Teilmodell und P ein Abbildungsparameter des Sensors 102 ist.The following is a description of tagging (labeling) processing by the single model generation unit 150 , The single model generation unit 150 calculates a projection (two-dimensional projection image) by the 3D model sharing processor 130 generated partial model (see 9 ). The individual model generation unit calculates 150 the projection using the imaging parameters (viewing angle, camera orientation, distance to the object, etc.) of the sensor 102 so that's through the sensor 102 captured images and the projection of the sub-model are similar in perspective. In particular, the following relationship applies: $$\text{x}=\text{PX}\text{.}$$

wherein the lower case x is a coordinate in the by the area determination data acquisition unit 160 captured image data, the capital letter X is a coordinate in the sub-model and P an imaging parameter of the sensor 102 is.

The single model generation unit 150 superimposed on the area determination data acquisition unit 160 captured image data and the projection images of all sub-models. In particular, the single model generation unit sets 150 the pictures of the workpiece 320 and the clamping device 322 on top of each other so that their outlines match. The workpiece is provided with tags on the pixels of the projection images, which are determined by the area determination unit 170 certain area 330 of the workpiece 320 are included. The jig 322 is tagged on the pixels in the area 332 of the clamping device are included (see 10 ). In the drawing, pixels are provided with the reference symbol on the workpiece 340 designated and those on the jig with the reference numeral 342 designated.

The single model generation unit 150 depending on the degree of overlay between the pixels forming the projection of the partial model and the area of the workpiece or the clamping device, tags for the workpiece or the clamping device are applied to the relevant partial model. For example, brings the single model generation unit 150 the tags for the workpiece on the relevant three-dimensional sub-model if those of the pixels forming the projection of the three-dimensional sub-model that exceed a predetermined percentage are provided with tags on the workpiece (see 11 ). The single model generation unit also brings 150 the tags for the clamping device on the relevant three-dimensional sub-model if those of the pixels forming the projection of the three-dimensional sub-model that exceed the predetermined percentage are provided with tags on the clamping device. For example, suppose that when a particular three-dimensional sub-model is projected to generate a two-dimensional image, 80 percent of the pixels of the projection image on the workpiece are tagged, 10 percent are tagged on the jig, and the remaining 10 percent are unknown (or not tagged). In this case, for security reasons, etc., jig tags can be attached to the pixels that have unknown or no tags. When this is done, 80 percent of the pixels of the projection image are tagged on the workpiece and 20 percent are tagged on the jig. If there is a rule that the larger number of tags attached to the pixels are used, for example, as tags for the sub-model, the individual model generation unit brings 150 in this case, workpiece tags on the three-dimensional part model. The single model generation unit 150 performs similar processing sequentially for all sub-models.

The following is a description of single-model generation processing by the single-model generation unit 150 , The single model generation unit 150 created using a part model tagged on the workpiece 350 a workpiece individual model and on the basis of a partial model provided with tags on the clamping device 352 a single clamping device model. The single model generation unit 150 can be set up to generate a plurality of individual models corresponding to the same day if the partial models with the same day do not touch each other. The single model generation unit 150 loads the single model into the 3D model memory 210 , where the single model based on the in the 3D model memory 210 saved partial models is obtained.

Thus, the individual models of the workpiece, the jig and the like, which are generated by the 3D model generating device 1 of the present embodiment, and in the 3D model memory 210 are stored, used in a machining simulation function and collision checking function of the numerical control device, collision checking device and the like.

Although an embodiment of the present invention is described herein, the invention is not limited to the above embodiment and can be appropriately modified and implemented in various ways.

In the above embodiment, the individual models of the workpiece and the clamping device are shown, for example, in such a way that they are generated on the basis of the integrated model, the workpiece and the clamping device are combined to which the workpiece is attached. Alternatively, however, individual models of a tool and a spindle can be generated using an integrated model that combines the tool and the spindle.

QUOTES INCLUDE IN THE DESCRIPTION

This list of documents listed by the applicant has been generated automatically and is only included for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent literature cited

• JP 4083554 [0004, 0007]
• JP 4456455 [0005, 0008]
• JP 6043234 [0006,0009]

Claims (4)

3D model generating device, which generates individual models, which suggest the individual shape of at least two objects, on the basis of an integrated model, which is generated on the basis of data obtained by jointly imaging or measuring the objects, and which is characterized in that it comprises: a 3D model division processor which generates a plurality of partial models by dividing the integrated model with extension planes which are obtained by expanding surfaces delimiting the integrated model, an area determination unit which determines two-dimensional areas in which the objects are present individually on the basis of the data obtained and a single model generation unit which tags the partial models based on projections of the partial models and the two-dimensional regions and generates the individual models of the objects on the basis of the labeled partial models. 3D model generation device according to Claim 1 , which is characterized in that the objects comprise a workpiece and a clamping device. 3D model generation device according to Claim 1 or 2 , which is characterized in that the area determination unit determines the two-dimensional areas based on luminance information or color information of recorded images of the objects. 3D model generation device according to one of the Claims 1 to 3 , which is characterized in that, depending on the degree of overlap between the projections of the partial models and the two-dimensional regions of the determined objects, the individual model generation unit attaches tags to the partial models that indicate the determined objects.

Images